Application of Deep and Machine Learning Using Image Analysis to Detect Fungal Contamination of Rapeseed

Abstract

This paper endeavors to evaluate rapeseed samples obtained in the process of storage experiments with different humidity (12% and 16% seed moisture content) and temperature conditions (25 and 30 °C). The samples were characterized by different levels of contamination with filamentous fungi. In order to acquire graphic data, the analysis of the morphological structure of rapeseeds was carried out with the use of microscopy. The acquired database was prepared in order to build up training, validation, and test sets. The process of generating a neural model was based on Convolutional Neural Networks (CNN), Multi-Layer Perceptron Networks (MLPN), and Radial Basis Function Networks (RBFN). The classifiers that were compared were devised on the basis of the environments Tensorflow (deep learning) and Statistica (machine learning). As a result, it was possible to achieve the lowest classification error of 14% for the test set, 18% classification error for MLPN, and 21% classification error for RBFN, in the process of recognizing mold in rapeseed with the use of CNN.

Deep and Machine Learning Using SEM, FTIR, and Texture Analysis to Detect Polysaccharide in Raspberry Powders

“…Network simulation was based on the Anaconda environment and packages for deep learning, i.e., TensorFlow and Keras. The TensorFlow package allows a substantial shortening of calculating time related to training artificial neural networks, especially related to image processing, thanks to parallel calculations with the GPU set [ 10 , 40 ]. The functions and methods of the Keras package allow efficient preparation of input data for the neural network [ 10 , 17 ].…”

“…The TensorFlow package allows a substantial shortening of calculating time related to training artificial neural networks, especially related to image processing, thanks to parallel calculations with the GPU set [ 10 , 40 ]. The functions and methods of the Keras package allow efficient preparation of input data for the neural network [ 10 , 17 ]. As a result of the learning process in 214 iterations, an adequate convolution network was acquired, which was characterized by the highest classification capability.…”

“…Artificial neural networks are most commonly used in terms of data, which do not have simple and organized structure calculations. ANN are used above all in stochastic issues, and the ones related to information processing, among other things, with images (bitmap) [ 10 ], acoustic emission [ 13 ], and numerical data [ 14 , 15 ]. The networks were also used in the process of deep learning, which includes extended methods of image processing.…”

“…The networks were also used in the process of deep learning, which includes extended methods of image processing. One should not forget that Convolutional Neural Networks (CNN) [ 10 , 16 ] are enjoying more and more popularity. CNN allows prediction [ 17 , 18 ], classification [ 19 ], analysis, data association, signal filtering, and process optimization [ 20 , 21 ] in a much shorter time.…”

“…It is worth noting down that also an innovative way of spray drying was used in the paper, which differs from traditional solutions. It should also be added that one of the methods of artificial intelligence in the form of artificial neural networks (ANN), whose functioning is based on using appropriate mathematical or programming formulas, was used in the Sensors 2021, 21, 5823 2 of 14 paper [10][11][12]. Artificial neural networks are most commonly used in terms of data, which do not have simple and organized structure calculations.…”